According to a recent LangChain Blog post, planning for agents remains a critical challenge for developers working with large language models (LLMs). The article delves into the intricacies of planning and reasoning, current fixes, and future expectations for agent planning.

What Exactly Is Meant by Planning and Reasoning?

Planning and reasoning by an agent involve the LLM’s ability to decide on a series of actions based on available information. This includes both short-term and long-term steps. The LLM evaluates all available data and decides on the first step it should take immediately, followed by subsequent actions.

Most developers use function calling to enable LLMs to choose actions. While function calling helps in immediate actions, long-term planning remains a significant challenge.

Current Fixes to Improve Planning by Agents

One of the simplest fixes is ensuring the LLM has all the necessary information to reason and plan appropriately. Adding a retrieval step or clarifying prompt instructions can significantly improve outcomes.

Changing the cognitive architecture of the application can also enhance planning. General-purpose architectures may be too general for practical use, leading to the preference for domain-specific cognitive architectures.

General Purpose vs. Domain Specific Cognitive Architectures

General-purpose cognitive architectures aim to improve reasoning generically, while domain-specific cognitive architectures are tailored to specific tasks.

Why Are Domain Specific Cognitive Architectures So Helpful?

Domain-specific cognitive architectures help by providing explicit instructions, effectively removing some planning responsibilities from the LLM.

Nearly all advanced agents in production utilize highly domain-specific and custom cognitive architectures. LangChain makes building these custom architectures easier with LangGraph, designed for high controllability.

The Future of Planning and Reasoning

The LLM space is expected to continue evolving rapidly. General-purpose reasoning is likely to become more integrated into the model layer, but there will always be a need to communicate specific instructions to the agent.

LangChain remains optimistic about the future of LangGraph, believing that as LLMs improve, the need for custom architectures will persist. The company is committed to enhancing the controllability and reliability of these architectures.

Image source: Shutterstock